Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 885 747 157 373  47 919 221 687 563 588 293 985 522 959 368 569 711 892 580 910
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 580 569 522 885 221 919 959 373 910  NA 563 747 157 687 985 293 892 368 588  47  NA 711  NA
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 4 5 5 3 3 4 3 4 3 1
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "y" "i" "l" "u" "k" "K" "F" "E" "U" "G"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  6 12 14 20
which( manyNumbersWithNA > 900 )
[1]  6  7  9 15
which( is.na( manyNumbersWithNA ) )
[1] 10 21 23

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 919 985 959 910
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 919 985 959 910
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 919 985 959 910

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "K" "F" "E" "U" "G"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "y" "i" "l" "u" "k"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE  TRUE FALSE  TRUE  TRUE FALSE FALSE  TRUE FALSE
which( manyNumbers %in% 300:600 )
[1]  4  9 10 13 15 16 19
sum( manyNumbers %in% 300:600 )
[1] 7

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" "large" "large" "large" "small" "large" "large" "small" "large" NA      "large" "large" "small" "large" "large" "small" "large" "small" "large" "small"
[21] NA      "large" NA     
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "large"   "large"   "large"   "small"   "large"   "large"   "small"   "large"   "UNKNOWN" "large"   "large"   "small"   "large"   "large"   "small"  
[17] "large"   "small"   "large"   "small"   "UNKNOWN" "large"   "UNKNOWN"
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 580 569 522 885   0 919 959   0 910  NA 563 747   0 687 985   0 892   0 588   0  NA 711  NA

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 4 5 3 1
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  4  5  3  1
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE FALSE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 15
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 985
which.min( manyNumbersWithNA )
[1] 20
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 47
range( manyNumbersWithNA, na.rm = TRUE )
[1]  47 985

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 580 569 522 885 221 919 959 373 910  NA 563 747 157 687 985 293 892 368 588  47  NA 711  NA
sort( manyNumbersWithNA )
 [1]  47 157 221 293 368 373 522 563 569 580 588 687 711 747 885 892 910 919 959 985
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  47 157 221 293 368 373 522 563 569 580 588 687 711 747 885 892 910 919 959 985  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 985 959 919 910 892 885 747 711 687 588 580 569 563 522 373 368 293 221 157  47  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 580 569 522 885 221
order( manyNumbersWithNA[1:5] )
[1] 5 3 2 1 4
rank( manyNumbersWithNA[1:5] )
[1] 4 3 2 5 1
sort( mixedLetters )
 [1] "E" "F" "G" "i" "k" "K" "l" "u" "U" "y"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 6.0 2.0 7.0 4.5 8.0 9.5 2.0 9.5 4.5 2.0
rank( manyDuplicates, ties.method = "min" )
 [1] 6 1 7 4 8 9 1 9 4 1
rank( manyDuplicates, ties.method = "random" )
 [1]  6  2  7  4  8 10  1  9  5  3

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000 -0.2336108 -0.8968313  0.4820128  0.3364524 -0.1373185 -1.1637040 -0.9785639 -0.6572674  0.7703953
[15]  1.0210586
round( v, 0 )
 [1] -1  0  0  0  1  0 -1  0  0  0 -1 -1 -1  1  1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.2 -0.9  0.5  0.3 -0.1 -1.2 -1.0 -0.7  0.8  1.0
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.23 -0.90  0.48  0.34 -0.14 -1.16 -0.98 -0.66  0.77  1.02
floor( v )
 [1] -1 -1  0  0  1 -1 -1  0  0 -1 -2 -1 -1  0  1
ceiling( v )
 [1] -1  0  0  1  1  0  0  1  1  0 -1  0  0  1  2

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2024 Biomedical Data Sciences (BDS) | LUMC